Triple
T16485720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Cummings |
E400433
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Mary Elliott
Mary Elliott was the wife of American actor Robert Cummings, known for her marriage to the film and television star.
|
E1285778
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Mary Elliott | Statement: [Robert Cummings, spouse, Mary Elliott]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Elliott Context triple: [Robert Cummings, spouse, Mary Elliott]
-
A.
Mary Ellis
Mary Ellis was a British actress known for her work on stage and screen in the early to mid-20th century.
-
B.
Elisabeth Scott
Elisabeth Scott was a pioneering British architect best known for designing the modernist Royal Shakespeare Theatre in Stratford-upon-Avon.
-
C.
Mary Ruthven
Mary Ruthven was a 17th-century Scottish noblewoman best known as the wife of Flemish Baroque painter Sir Anthony van Dyck and a lady-in-waiting to Queen Henrietta Maria.
-
D.
Jane Doughty
Jane Doughty is a technology entrepreneur best known as one of the founders of the database software company Sybase.
-
E.
Mary Tomlinson
Mary Tomlinson is the birth name of American character actress Marjorie Main, best known for her comedic roles in mid-20th-century Hollywood films.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mary Elliott Triple: [Robert Cummings, spouse, Mary Elliott]
Generated description
Mary Elliott was the wife of American actor Robert Cummings, known for her marriage to the film and television star.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mary Elliott Target entity description: Mary Elliott was the wife of American actor Robert Cummings, known for her marriage to the film and television star.
-
A.
Mary Ellis
Mary Ellis was a British actress known for her work on stage and screen in the early to mid-20th century.
-
B.
Elisabeth Scott
Elisabeth Scott was a pioneering British architect best known for designing the modernist Royal Shakespeare Theatre in Stratford-upon-Avon.
-
C.
Mary Ruthven
Mary Ruthven was a 17th-century Scottish noblewoman best known as the wife of Flemish Baroque painter Sir Anthony van Dyck and a lady-in-waiting to Queen Henrietta Maria.
-
D.
Jane Doughty
Jane Doughty is a technology entrepreneur best known as one of the founders of the database software company Sybase.
-
E.
Mary Tomlinson
Mary Tomlinson is the birth name of American character actress Marjorie Main, best known for her comedic roles in mid-20th-century Hollywood films.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d883813098819084f5409539723b59 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e068fac8190a0971f548848fcfe |
completed | April 18, 2026, 7:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0242d952988190b9b3eaca8fa92431 |
completed | May 11, 2026, 8:58 p.m. |
| NEDg | Description generation | batch_6a0246f31c8c819097685337f0f14dad |
completed | May 11, 2026, 9:15 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a02478d775c8190ac9d14bd260e7eca |
completed | May 11, 2026, 9:18 p.m. |
Created at: April 10, 2026, 5:13 a.m.